CN105678030B - Divide the air-combat tactics team emulation mode of shape based on expert system and tactics tactics - Google Patents
Divide the air-combat tactics team emulation mode of shape based on expert system and tactics tactics Download PDFInfo
- Publication number
- CN105678030B CN105678030B CN201610121117.4A CN201610121117A CN105678030B CN 105678030 B CN105678030 B CN 105678030B CN 201610121117 A CN201610121117 A CN 201610121117A CN 105678030 B CN105678030 B CN 105678030B
- Authority
- CN
- China
- Prior art keywords
- tactics
- air
- team
- combat
- library
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/36—Circuit design at the analogue level
- G06F30/367—Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
Landscapes
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses the air-combat tactics team emulation modes for dividing shape based on expert system and tactics tactics, this method passes through following steps and realizes: working knowledge establishes, the mathematical method of the representation of knowledge and processing, carry out simulation modeling, each tactics and tactics are accordingly converted into a data set, and calling is stored in a manner of library or word bank；Building divides shape tactics library；Establish the tactics index system of a set of evaluation tactics team fighting efficiency；Establish air battle knowledge self learning mechanism；Tactics inference mechanism is established using artificial intelligence technology；Tactics reconstruct: the smooth transition i.e. between realization tactics and tactics or tactics and tactics.This method is tried out and is verified in scientific research project, blue party Virtual Intelligent tactics team is established with this method, red air-combat simulation trainer need only operate and commander on party B flight simulation platform, the overall process no-data region dual training with opponent can be realized automatically, not only hardware size is reduced, but also training difficulty can be improved.
Description
Technical field
The present invention relates to operation simulation technical fields, and in particular to a kind of to divide shape based on expert system and tactics tactics
Air-combat tactics team emulation mode, this method construct blue party Virtual Intelligent tactics team, realize " people-machine " tactical confrontation.
Background technique
The base model of Lock on is formation air fighting, and double, four machines formation is basic battle formation.Utilizing emulation system
When system carries out air-combat tactics simulated training, there are two kinds of situations: first is that too many man in the loop simulator once can not be equipped with；
Second is that pilot cannot really embody countermeasures simulation effect and Weapon Combat when the unskilled machine of driving carries out emulation confrontation
Efficiency.The tactics research for being unfolded to be directed to F22 is such as needed, normal flight person drives F22 Warfighter Simulation device, flies due to not grasping F22
The performance and tactics of machine can not really play its fighting efficiency, the effect of confrontation are not achieved.The application proposition solves the problems, such as this
Method is: building blue party Virtual Intelligent tactics team, the whole battle of blue party when which represents air-combat tactics simulated training
Strength (including pilot, commander, other civilian war service personnel and related tactics tactics application etc.).It is not 1 pair 1 of simple confrontation,
But the confrontation of the multi-to-multi between team and team.
Therefore, building blue party Virtual Intelligent tactics team relates to virtual aircraft, virtual command, at tactics tactics knowledge
Many-sided emulation technology such as reason and Simulation Application.In terms of virtual aircraft, there are mainly two types of methods at present: first is that troops generate skill
Multi rack virtual aircraft may be implemented in art, but these aircrafts are run according to advance planning scheme, without intelligence confrontation function；Second is that
Single rack virtual aircraft realizes technology, and method is relatively more, optimizes both for position between ourselves and the enemy, to reach best state
The case where gesture implements attack, but these technology and methods do not account for multi-aircraft cooperative combat, cannot achieve multi-aircraft
Cooperation.
Summary of the invention
The problem of for background technique, the purpose of the present invention is to provide one kind to be fought based on expert system and tactics
Method divides the air-combat tactics team emulation mode of shape, establishes blue party Virtual Intelligent tactics team, red air battle mould with this method
Quasi- trainer need only operate and be commanded on party B flight simulation platform, can realize that the overall process air battle with opponent is imitative automatically
True dual training not only reduces hardware size, but also can improve training difficulty.
The purpose of the present invention is achieved through the following technical solutions:
Divide the air-combat tactics team emulation mode of shape based on expert system and tactics tactics, the air-combat tactics team is imitative
True method includes the following steps:
1) mathematical method of working knowledge foundation, the representation of knowledge and processing, carries out simulation modeling, each tactics and tactics
It is all accordingly converted into a data set, by type and feature by each data set, calling is stored in a manner of library or word bank；
2) fractal theory, artificial intelligence and expert system are used, a point shape, building point are carried out to multinomial elementary tactic and tactics
Shape tactics library；
3) principal element in air battle confrontation is analyzed, studies mutual relationship, develops many indexes pair
The model answered establishes the tactics index system of a set of evaluation tactics team fighting efficiency, the foundation as reasoning and study；
4) air battle knowledge self learning mechanism is established, the air combat situation knowledge base enriched constantly characterized by air combat situation is empty
A kind of study mechanism of the knowledge self learning mechanism of fighting using " priori "+" posteriority " mode, foundation Synthetic Tactics evaluation index system,
By study, knowledge base of enriching constantly and rule base；
5) tactics inference mechanism is established using artificial intelligence technology, using the tactics assessment indicator system having built up, and
It is associated with current situation, optimization and automatic selection in next step this how to take countereffort, both current tactics still more renew
Tactics；
6) tactics reconstructs: the smooth transition i.e. between realization tactics and tactics or tactics and tactics.
Further, construction step 2) described in divide the method in shape tactics library specifically: based on time slice sampling method,
Cast out red blue both sides' air battle it is initial when cruise time divide shapeization to handle since a side has found other side tactics process, use
Dynamic step length record divided shape fiducial time by 5 seconds or 1 second respectively before and after weapon intercepts and captures target for a tactics, one is fought
Method is divided into several fracton tactics, and the constitution element of every sub- tactics is as follows:
Aircraft state collection: { type, quantity, number, time, position and attitude, speed, radar state, disturbance state }；
Guided missile state set: { model, time, position and attitude, speed }；
Sub- tactics typing feature database is saved, to constitute a point of shape tactics library.
Further, tactics described in step 6) reconstructs specifically: protects according to current aerial situation by reasoning and judging
Tactics is held or replaced, current data is read from described point of shape tactics library by instruction, passes through the orthodox flight solution of equation of point-to-point transmission
It calculates, is smoothly transitted into the tactics of subsequent time.
Further, establishment step 3) in evaluation tactics team fighting efficiency tactics index system method specifically: it is right
Principal element in air battle confrontation is analyzed, and is studied mutual relationship, and study the model of many indexes, is established a set of
Evaluation " virtual flight person " tactics index system: aircraft detected probability, intercept probability, persistently track the time, injure probability,
Escape probability, war damage, weapon exchange than, probability of interference, anti-interference probability；Using these indexs as making inferences and learn
Foundation.
Further, the air battle knowledge self learning mechanism in step 4) specifically: the air battle knowledge self learning mechanism
Using a kind of study mechanism of " priori "+" posteriority " mode, the situation of air battle both sides is first obtained, by the way of man-computer cooperation,
Situation is analyzed, is judged according to expertise and existing rule, current move is obtained from limited action behavior library
Make, preparatory comprehensive assessment then is carried out to such movement and is optimal if meeting condition, then knowing as affirmative
Storage is known into library, if being unsatisfactory for condition, is also carried out learning records, is then replaced another behavior act, be optimal
Until, if be not all optimal, just from the optimal movement in used movement, forms a new knowledge and be stored in library
In.
Further, establishment step 5) in the tactics inference mechanism specifically:
For shape tactics library is divided, tactics instruction is designed are as follows:
f<In+1,An+1,Tn+1>=f (In,An,Tn, red situation)
Wherein:
In、In+1Respectively indicate forward and backward moment or time step formation parameter；
An、An+1Respectively indicate forward and backward moment or time step aircraft state parameter；
Tn、Tn+1Respectively indicate forward and backward moment or time step situation parameter；
Above-mentioned function is mainly completed to resolve new formation according to present formation, position and the situation of enemy, the shadow in formation
Ring In+1, specifically:
Aircraft damage situation is resolved according to existing calculation method, quantitatively influences In+1；
According to injuring situation, if replacement leader number；
According in In+1And Tn+1Under clear, formation indeterminate case, the multiple A interrogated are looked into a point shape tactics libraryn+1Further place
Reason, takes and AnApart from nearest An+1, construct new formation.
The present invention has following positive technical effect:
Blue party Virtual Intelligent tactics team is established with method disclosed in the present application, red air-combat simulation trainer is only
It must operate and command on party B flight simulation platform, can realize the overall process no-data region dual training with opponent automatically,
Not only hardware size is reduced, but also training difficulty can be improved.
Detailed description of the invention
Fig. 1 is virtual tactics team principle of simulation block diagram of the invention；
Fig. 2 is tactics team autonomous learning model of the invention；
Fig. 3 is tactics knowledge base block diagram of the invention；
Fig. 4 is Inference Expert Systems flow diagram of the invention.
Specific embodiment
In the following, being made a more thorough explanation with reference to attached drawing to the present invention, shown in the drawings of exemplary implementation of the invention
Example.However, the present invention can be presented as a variety of different forms, it is not construed as the exemplary implementation for being confined to describe here
Example.And these embodiments are to provide, to keep the present invention full and complete, and it will fully convey the scope of the invention to this
The those of ordinary skill in field.
The spatially relative terms such as "upper", "lower" " left side " " right side " can be used herein for ease of explanation, for saying
Relationship of the elements or features relative to another elements or features shown in bright figure.It should be understood that in addition in figure
Except the orientation shown, spatial terminology is intended to include the different direction of device in use or operation.For example, if in figure
Device is squeezed, and is stated as being located at other elements or the element of feature "lower" will be located into other elements or feature "upper".Cause
This, exemplary term "lower" may include both upper and lower orientation.Device, which can be positioned in other ways, (to be rotated by 90 ° or is located at
Other orientation), it can be interpreted accordingly used herein of the opposite explanation in space.
As shown in Figure 1, the air-combat tactics team emulation mode for dividing shape based on expert system and tactics tactics of the application
Include the following steps:
1. combing, analysis are accepted or rejected and induction and conclusion tactics, working knowledge established, the mathematical method of the representation of knowledge and processing,
Carry out simulation modeling, each tactics and tactics are accordingly converted into a data set, each data set by type and feature, with
The mode of library or word bank stores calling.
2. carrying out a point shape, building point to multinomial elementary tactic and tactics using fractal theory, artificial intelligence and expert system
Shape tactics library.
3. the principal element in pair air battle confrontation is analyzed, mutual relationship is studied, many indexes are developed
Corresponding model establishes the tactics index system of a set of evaluation tactics team fighting efficiency, the foundation as reasoning and study.
4. establishing air battle knowledge self learning mechanism, the air combat situation knowledge base (rule enriched constantly characterized by air combat situation
Then library), air battle knowledge self learning mechanism is assessed using a kind of study mechanism of " priori "+" posteriority " mode according to Synthetic Tactics
Index system, by study, knowledge base of enriching constantly and rule base.
5. establish tactics inference mechanism using artificial intelligence technology, using having built up tactics assessment indicator system, and with
Current situation is associated, to optimization and automatic selection in next step this how to take countereffort, both current tactics still more renew
Tactics.
6. tactics reconstructs, the smooth transition between tactics (tactics) and tactics (tactics) is realized.
By above step, according to the main basic program operational process of Fig. 1, the air battle war with certain intelligence is constructed
Art team opponent.
One of the core technology of virtual tactics team Simulation Methods tactics divides shape and reconstruct.
Detailed process is as follows for tactics Fractal process:
In tactics segmentation, tactics length is selected, needs to consider two aspect factors, if the tactics length divided is too big,
Cause tactics replacement not in time, situation of battlefield adaptability to changes is poor, if tactics length is too small, will cause the operation efficiency of system too
It is low.When dividing to tactics, be based on time slice sampling method, cast out red blue both sides' air battle it is initial when cruise when
Between, since a side has found other side, divides shapeization to handle tactics process, recorded using dynamic step length, before weapon intercepts and captures target
Divide shape fiducial time (subsequent descriptions) by 5 seconds, 1 second respectively afterwards for a tactics, a tactics can be divided into several point of shape
Sub- tactics (usually within 200), the constitution element of every sub- tactics:
Aircraft state collection: { type, quantity, number, time, position and attitude (x, y, z, φ, θ, γ), speed (Vx Vy
Vz), radar state, disturbance state }；
Guided missile state set: { model, time, position and attitude (x, y, z, φ, θ, γ), speed (Vx Vy Vz)}
Sub- tactics typing feature database is saved, a point of shape tactics library is constituted；Fractal process such as is carried out to 100 tactics,
The library will have 20000 tactics.
Detailed process is as follows for tactics reconstruct:
Tactics reconstruct is both by reasoning and judging, to keep or replacement tactics according to current aerial situation, by instruction from point
Shape tactics reads current data in library, by the orthodox flight equation solver of point-to-point transmission, is smoothly transitted into the tactics of subsequent time.
For guarantee tactics replacement when smooth transition, tactics storage and resolve optimization, and with campaign information be easier in real time it is right
The factors such as connect, through overtesting, statistics and analysis, if taking 1 second as a tactics point shape fiducial time, flying distance only has several hundred rice,
This fiducial time can satisfy the smooth replacement of tactics.
Principal element in air battle confrontation is analyzed, studies mutual relationship, and study the mould of many indexes
Type establishes a set of evaluation " virtual flight person " tactics index system: aircraft detected probability, intercept probability, when persistently tracking
Between, injure probability, escape probability, war damage, weapon exchange than, probability of interference, anti-interference probability.Using these indexs as progress
The foundation of reasoning and study.
As shown in Fig. 2, air battle knowledge self learning mechanism is first obtained using a kind of study mechanism of " priori "+" posteriority " mode
The situation for taking air battle both sides analyzes situation by the way of man-computer cooperation, is sentenced according to expertise and existing rule
It is disconnected, current movement is obtained from limited action behavior library, preparatory comprehensive assessment then is carried out to such movement, if full
Sufficient condition, is optimal, then the knowledge store as an affirmative is into library, if being unsatisfactory for condition, also carries out learning records,
Then another behavior act is replaced, until being optimal, if be not all optimal, just from used movement
Optimal movement forms a new knowledge and is stored in library.
As shown in figure 3, third generation fighter duel is generally carried out with a cooperative mode of forming into columns and form into columns.To make knowledge base knot
Structure is clear, establishes knowledge base according to several big elements of the posture of operation, the production of various air combat situations is established according to type, formation quantity
Raw formula rule, the movement after the corresponding instruction of every kind of situation and reception instruction is all different, and whole rules are both collected in flight
In knowledge base.The application uses common production rule, completes the coding of flight knowledge base, and every rule has two parts,
That is condition and conclusion.
As shown in figure 4, the instruction that inference machine generates also is not achieved by the conclusion of knowledge base inferred in air combat process
It is required that, it is necessary to incorporate the calculating of many situation variations.For shape tactics library is divided, tactics instruction is designed are as follows:
f<In+1,An+1,Tn+1>=f (In,An,Tn, red situation)
Wherein:
In、In+1Respectively indicate forward and backward moment (or time step) formation parameter；
An、An+1Respectively indicate forward and backward moment (or time step) aircraft state parameter；
Tn、Tn+1Respectively indicate forward and backward moment (or time step) situation parameter.
Function is mainly completed to resolve new formation according to present formation, position and the situation of enemy, influences in formation
In+1, it is specific:
1. resolving aircraft damage situation according to existing calculation method, I is quantitatively influencedn+1
2. according to situation is injured, if replacement leader number,
3. according in In+1And Tn+1Under clear, formation indeterminate case, the multiple A interrogated are looked into a point shape tactics libraryn+1Further
Processing, takes and AnApart from nearest An+1, construct new formation.
It is described above simply to illustrate that of the invention, it is understood that the present invention is not limited to the above embodiments, meets
The various variants of inventive concept are within the scope of the present invention.
Claims (6)
1. dividing the air-combat tactics team emulation mode of shape based on expert system and tactics tactics, which is characterized in that the air battle
Tactics team emulation mode includes the following steps:
1) mathematical method of working knowledge foundation, the representation of knowledge and processing, carries out simulation modeling, each tactics and tactics are right
It is converted into a data set with answering, by type and feature by each data set, calling is stored in a manner of library or word bank；
2) fractal theory, artificial intelligence and expert system are used, a point shape is carried out to multinomial elementary tactic and tactics, a building point shape is fought
Faku County；
3) principal element in air battle confrontation is analyzed, studies mutual relationship, it is corresponding develops many indexes
Model establishes the tactics index system of a set of evaluation tactics team fighting efficiency, the foundation as reasoning and study；
4) air battle knowledge self learning mechanism is established, the air combat situation knowledge base enriched constantly characterized by air combat situation, air battle is known
Know self-study mechanism to pass through using a kind of study mechanism of " priori "+" posteriority " mode according to Synthetic Tactics evaluation index system
Study, knowledge base of enriching constantly and rule base；
5) establish tactics inference mechanism using artificial intelligence technology, using the tactical assessment index system having built up, and with work as
Preceding situation is associated, and how this takes countereffort to optimization and automatic selection next step, i.e., current tactics still more renew tactics；
6) tactics reconstructs: the smooth transition i.e. between realization tactics and tactics or tactics and tactics.
2. the air-combat tactics team emulation mode according to claim 1 for dividing shape based on expert system and tactics tactics,
It is characterized by: construction step 2) described in divide the method in shape tactics library specifically: based on time slice sampling method, cast out
Tactics process is divided shapeization to handle, using dynamic by cruise time when red indigo plant both sides air battle is initial since a side has found other side
Step-length record divided shape fiducial time by 5 seconds or 1 second respectively before and after weapon intercepts and captures target for a tactics, by a tactics point
Constitution element for several fracton tactics, every sub- tactics is as follows:
Aircraft state collection: { type, quantity, number, time, position and attitude, speed, radar state, disturbance state }；
Guided missile state set: { model, time, position and attitude, speed }；
Sub- tactics typing feature database is saved, to constitute a point of shape tactics library.
3. the air-combat tactics team emulation mode according to claim 1 for dividing shape based on expert system and tactics tactics,
It is characterized by: tactics described in step 6) reconstructs specifically: according to current aerial situation, by reasoning and judging, keep or
Tactics is replaced, reads current data from described point of shape tactics library by instruction, by the orthodox flight equation solver of point-to-point transmission, is put down
The sliding tactics for being transitioned into subsequent time.
4. the air-combat tactics team emulation mode according to claim 1 for dividing shape based on expert system and tactics tactics,
It is characterized by: establishment step 3) in evaluation tactics team fighting efficiency tactics index system method specifically: to air battle
Principal element in confrontation is analyzed, and mutual relationship is studied, and studies the model of many indexes, establishes a set of evaluation
" virtual flight person " tactics index system: { aircraft detected probability, intercept probability persistently track the time, injure probability, escape
Probability, war damage, weapon exchange than, probability of interference, anti-interference probability；Using these indexs as the foundation for making inferences and learning.
5. the air-combat tactics team emulation mode according to claim 1 for dividing shape based on expert system and tactics tactics,
It is characterized by: the air battle knowledge self learning mechanism in step 4) specifically: the air battle knowledge self learning mechanism uses
A kind of study mechanism of " priori "+" posteriority " mode, first obtains the situation of air battle both sides, by the way of man-computer cooperation, to state
Gesture is analyzed, and is judged according to expertise and existing rule, is obtained current movement from limited action behavior library, so
It carries out preparatory comprehensive assessment to such movement afterwards to be optimal if meeting condition, then the knowledge store as an affirmative
Into library, if being unsatisfactory for condition, learning records are also carried out, then replace another behavior act, until being optimal, such as
Fruit is not all optimal, and just from the optimal movement in used movement, forms a new knowledge and is stored in library.
6. air-combat tactics team according to claim 1 emulation mode, which is characterized in that establishment step 5) in the war
Method inference mechanism specifically: for shape tactics library is divided, tactics instruction is designed are as follows:
f<In+1,An+1,Tn+1>=f (In,An,Tn, red situation)
Wherein:
In、In+1Respectively indicate forward and backward moment or time step formation parameter；
An、An+1Respectively indicate forward and backward moment or time step aircraft state parameter；
Tn、Tn+1Respectively indicate forward and backward moment or time step situation parameter；
Function is mainly completed to resolve new formation according to present formation, position and the situation of enemy, and I is influenced in formationn+1, tool
Body are as follows:
Aircraft damage situation is resolved according to existing calculation method, quantitatively influences In+1；
According to injuring situation, if replacement leader number；
According in In+1And Tn+1Under clear, formation indeterminate case, the multiple A interrogated are looked into a point shape tactics libraryn+1It is further processed,
It takes and AnApart from nearest An+1, construct new formation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610121117.4A CN105678030B (en) | 2016-03-03 | 2016-03-03 | Divide the air-combat tactics team emulation mode of shape based on expert system and tactics tactics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610121117.4A CN105678030B (en) | 2016-03-03 | 2016-03-03 | Divide the air-combat tactics team emulation mode of shape based on expert system and tactics tactics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105678030A CN105678030A (en) | 2016-06-15 |
| CN105678030B true CN105678030B (en) | 2019-09-27 |
Family
ID=56307741
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610121117.4A Expired - Fee Related CN105678030B (en) | 2016-03-03 | 2016-03-03 | Divide the air-combat tactics team emulation mode of shape based on expert system and tactics tactics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105678030B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105844068B (en) * | 2016-06-16 | 2018-11-13 | 中国人民解放军国防科学技术大学 | A kind of Q learning attack target assignment methods of Simulation-Oriented |
| CN106682351A (en) * | 2017-01-10 | 2017-05-17 | 北京捷安申谋军工科技有限公司 | Fight simulation system generating military strength based on computer and simulation method |
| CN106952014B (en) * | 2017-02-10 | 2018-03-02 | 南京航空航天大学 | A kind of battle plan optimization method based on Military Simulation device |
| CN109656147A (en) * | 2018-11-23 | 2019-04-19 | 中国航空工业集团公司沈阳飞机设计研究所 | Air-combat simulation system |
| CN111308907B (en) * | 2019-12-20 | 2023-04-18 | 中国航空工业集团公司沈阳飞机设计研究所 | Automatic battle-level airplane simulation control method, control plug-in and simulation system |
| CN111460730A (en) * | 2020-03-26 | 2020-07-28 | 中国电子科技集团公司第二十八研究所 | Future combat intelligent technology application design method |
| CN112598046B (en) * | 2020-12-17 | 2023-09-26 | 沈阳航空航天大学 | Target tactical intent recognition method in multi-machine cooperative air combat |
| CN113126648B (en) * | 2021-02-18 | 2022-07-05 | 西北工业大学 | Four-rotor unmanned aerial vehicle cooperative control method based on expert S-plane control |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6195626B1 (en) * | 1998-06-19 | 2001-02-27 | Microsoft Corporation | Heightened realism for computer-controlled units in real-time simulation |
| CN102063902A (en) * | 2010-11-04 | 2011-05-18 | 黄安祥 | High-efficient voice instruction recognition method based on fuzzy theory and expert system |
| CN102508232A (en) * | 2011-10-20 | 2012-06-20 | 黄安祥 | Multi-source detection-based method for detecting stealth target in the sky |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5378155A (en) * | 1992-07-21 | 1995-01-03 | Teledyne, Inc. | Combat training system and method including jamming |
| CN104484500A (en) * | 2014-09-03 | 2015-04-01 | 北京航空航天大学 | Air combat behavior modeling method based on fitting reinforcement learning |
-
2016
- 2016-03-03 CN CN201610121117.4A patent/CN105678030B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6195626B1 (en) * | 1998-06-19 | 2001-02-27 | Microsoft Corporation | Heightened realism for computer-controlled units in real-time simulation |
| CN102063902A (en) * | 2010-11-04 | 2011-05-18 | 黄安祥 | High-efficient voice instruction recognition method based on fuzzy theory and expert system |
| CN102508232A (en) * | 2011-10-20 | 2012-06-20 | 黄安祥 | Multi-source detection-based method for detecting stealth target in the sky |
Non-Patent Citations (2)
| Title |
|---|
| 基于云计算平台的航空兵训练仿真体系结构;黄安祥等;《系统仿真学报》;20110715;第23卷(第S1期);第106页至109页 * |
| 基友Skyline的空战仿真数据三维可视化回放研究;雷祥等;《系统仿真学报》;20130808;第25卷(第8期);第1881页至1885页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105678030A (en) | 2016-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105678030B (en) | Divide the air-combat tactics team emulation mode of shape based on expert system and tactics tactics | |
| CN110929394B (en) | Combined combat system modeling method based on super network theory and storage medium | |
| CN113791634B (en) | Multi-agent reinforcement learning-based multi-machine air combat decision method | |
| CN111240353B (en) | Unmanned aerial vehicle collaborative air combat decision method based on genetic fuzzy tree | |
| CN101964019A (en) | Against behavior modeling simulation platform and method based on Agent technology | |
| CN112198892B (en) | Multi-unmanned aerial vehicle intelligent cooperative penetration countermeasure method | |
| CN113893539B (en) | Cooperative fighting method and device for intelligent agent | |
| CN112820164A (en) | Layered behavior model-based VR virtual confrontation training system | |
| CN115291625A (en) | Multi-unmanned aerial vehicle air combat decision method based on multi-agent layered reinforcement learning | |
| CN109597839B (en) | Data mining method based on avionic combat situation | |
| CN109541960B (en) | System and method for aircraft digital battlefield confrontation | |
| CN114638339A (en) | Intelligent agent task allocation method based on deep reinforcement learning | |
| CN113723013A (en) | Multi-agent decision method for continuous space chess deduction | |
| Wu et al. | Visual range maneuver decision of unmanned combat aerial vehicle based on fuzzy reasoning | |
| Kong et al. | Hierarchical multi‐agent reinforcement learning for multi‐aircraft close‐range air combat | |
| CN113625569A (en) | Small unmanned aerial vehicle prevention and control hybrid decision method and system based on deep reinforcement learning and rule driving | |
| CN113741186B (en) | Double-aircraft air combat decision-making method based on near-end strategy optimization | |
| CN113312789A (en) | Simulation system and method based on multi-information fusion | |
| CN117291254A (en) | Agent task allocation training method based on imitation learning and safety reinforcement learning | |
| Karneeb et al. | Distributed discrepancy detection for a goal reasoning agent in beyond-visual-range air combat | |
| CN116520884A (en) | Unmanned plane cluster countermeasure strategy optimization method based on hierarchical reinforcement learning | |
| Kong et al. | Multi-ucav air combat in short-range maneuver strategy generation using reinforcement learning and curriculum learning | |
| CN116432030A (en) | Air combat multi-intention strategy autonomous generation method based on deep reinforcement learning | |
| CN114330093A (en) | Multi-platform collaborative intelligent confrontation decision-making method for aviation soldiers based on DQN | |
| Hu et al. | A Neural Network-Based Intelligent Decision-Making in the Air-Offensive Campaign with Simulation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190927 Termination date: 20200303 |